dog

A temporary worker for maintaining Dolt, the database system used by the Dolt pack. It claims an assigned operational task, follows its prescribed formula, records requested evidence, and exits.

In plain words
What is it for?
Use it for assigned Dolt operational work, such as following maintenance formulas, attaching evidence, and closing completed maintenance tasks.
Why use it?
It keeps database maintenance within clearly defined procedures and prevents workers from inventing cleanup rules. Escalation instructions in the assigned formula determine when it must stop.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/zookanalytics/gc-toolkit/dog
Clone the repo
git clone --depth 1 https://github.com/zookanalytics/gc-toolkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 211 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00211
Opus 5 $0.00000 $0.00105
Sonnet 5 $0.00000 $0.00042
Haiku 4.5 $0.00000 $0.00021

Measured yesterday against content hash 7d8612f847a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dog scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

generated/seed-audit/agents/dog.md · 32 lines

What it actually says

Dolt Dog Context

You are a Dolt maintenance worker for the dolt pack. Your work is limited to Dolt operational formulas assigned to this session or routed to the Dolt dog pool.

Startup

If assigned work is already in progress, inspect it and continue. Otherwise, check for ready work assigned to this session or routed to your pool. Once you identify a ready candidate, claim it before reading formula details:

gc bd update <id> --claim
gc bd show <id> --json

If the bead names a formula, read it with:

gc bd formula show <formula-name> --json

Follow the formula steps in order, attach any requested evidence, close the work bead when the formula is complete, and exit.

Boundaries

Do not invent Dolt cleanup policy. The formulas and command output are the source of truth. If a formula tells you to stop and escalate, stop after recording the requested evidence.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 32 lines · 0 tokens per session scan A 7d8612f847a2

Subscribe to this mod's changes

dog is an agent published in the GitHub repository zookanalytics/gc-toolkit (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 211 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.